Learning to Extract Line Features: Beyond Split & Merge
Fulvio Mastrogiovanni, Antonio Sgorbissa, Zaccaria Renato · IOS Press eBooks · 2008
The paper deals with the role of line features in self-localization, when an extended Kalman filter is adopted. First, a theoretical analysis is introduced, showing how the amount of range measurements contributing to lines extracted from 2D range data affects the localization accuracy. Second, a novel approach for line extraction, which takes the theoretical analysis into accountis considered. Experimental results are used to discuss the main properties of the system.